submission 731915
ALL-FUN-d · python · License unknown
Use it
Vendorable · source mirrored · license unknownView source →
No package. Vendor the mirrored source: 23 lines, June 9 Researcher Reciprocity License v1.0.
submission.py
curl "https://kernelindex.com/api/v1/implementations/kernelbot-amd-mxfp4-mm-731915?include=source"interfacepython
Compatibility
measured onAMD Instinct MI355X
declared hardwareAMD Instinct MI355X
architecturesgfx950
dtypesbf16, mxfp4
Benchmark evidence
1 measurement across 1 GPU, fastest first.
Operation / workload
Hardware
Latency
Rank
Observed
Reported · How evidence levels are derived →
Source and license
sourceavailable
revision digestsha256:b55d6f26d7e60eaf067962b3d6dc080daf986410c64bcaa6e5b856f1858a4385
license declaredunknown
license concludedunknown
authorsALL-FUN-d
imported2026-08-26
Kernel source
submission.py23 lines
#!POPCORN leaderboard amd-mxfp4-mm
#!POPCORN gpu MI355X
import torch
from task import input_t, output_t
import aiter
from aiter import dtypes
from aiter.ops.triton.quant import dynamic_mxfp4_quant
from aiter.utility.fp4_utils import e8m0_shuffle
def custom_kernel(data: input_t) -> output_t:
A, B, B_q, B_shuffle, B_scale_sh = data
A_fp4, A_bs_e8m0 = dynamic_mxfp4_quant(A)
A_bs_e8m0 = e8m0_shuffle(A_bs_e8m0)
A_q = A_fp4.view(dtypes.fp4x2)
A_scale_sh = A_bs_e8m0.view(dtypes.fp8_e8m0)
return aiter.gemm_a4w4(
A_q, B_shuffle, A_scale_sh, B_scale_sh,
dtype=dtypes.bf16, bpreshuffle=True,
)
Source code from GPU Mode and the KernelBot dataset · June 9 Researcher Reciprocity License v1.0
Best evidence level for this revision: reported
JSON